基于转移学习的自动重量再分配组合模型,用于电力行业的泄漏检测
Sungsoo Kwon1, Seoyoung Jeon1, Tae-Jin Park2
1Department of AI and Big Data Engineering, Daegu Catholic University, 13-13, Hayang-ro, Hayang-eup, Gyeongsan-si 38430, Republic of Korea.
Sensors (Basel, Switzerland)
|August 10, 2024
概括
本研究介绍了一种使用转移学习 (TL) 进行精确泄漏检测的AI模型. 该方法有效地识别泄漏,即使数据有限,提高安全性和效率.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 声学信号处理 声学信号处理
背景情况:
- 将人工智能集成到发电厂行业需要强大的泄漏检测系统.
- 特定站点的人工智能方法在不同的操作环境中面临挑战.
- 准确诊断泄漏信号对于工厂的安全性和效率至关重要.
研究的目的:
- 开发一种有效的深度学习技术,用于在各种发电厂环境中诊断泄漏信号.
- 使用转移学习克服特定站点人工智能方法的局限性.
- 为了提高基于AI的泄漏检测的准确性和可靠性.
主要方法:
- 提出了一个基于转移学习 (TL) 的自动重量重新分配组合模型.
- 将时间序列的声学数据处理成3D根-平均-平方 (RMS) 和频率体积特征.
- 采用了两阶段的TL流程:初始的特定领域培训,然后通过软max分数调整重量以进行组合再培训.
主要成果:
- 拟议的方法有效地将低级泄漏与噪声区分开来.
- 即使使用非常有限的训练数据,也能实现准确的泄漏检测.
- 与现有技术相比,在各种环境中表现出优越的性能.
结论:
- 开发的基于TL的组合模型为动力发电厂的AI驱动泄漏检测提供了通用的解决方案.
- 这种方法通过解决数据稀缺性和环境多样性,提高了AI在工业环境中的适用性.
- 该技术通过可靠的泄漏识别,在确保发电厂的运行完整性方面取得了重大进展.
相关概念视频
Fast Decoupled and DC Powerflow
180
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
180
Multimachine Stability
150
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
150


